6 papers · 1 filter
Runaway Reaction: When Benign Skills Compose into Malicious Behavior
Zunlong Zhou, Ziyuan Yang, Mengyu Sun +1
Agent skills package task-specific knowledge and procedures that can be composed to support complex agent tasks, while public marketplaces provide a growing pool of reusable skills…
One-Time Training for All Grains: Open-Set Grain Recognition and Quantitative Analysis
Qihe Su, Mengyu Sun, Yuxi Ke +4
Advances in crop breeding have introduced an increasing number of grain varieties, creating a growing demand for efficient variety recognition and quantitative analysis. However, e…
Whispers in the Noise: Surrogate-Guided Concept Awakening via a Multi-Agent Framework
Mengyu Sun, Ziyuan Yang, Zunlong Zhou +3
Diffusion models (DMs) are widely used for text-to-image generation, but their strong generative capabilities also raise concerns about unsafe or undesirable content. Concept erasu…
Trust the Unreliability: Inward Backward Dynamic Unreliability Driven Coreset Selection for Medical Image Classification
Yan Liang, Ziyuan Yang, Zhuxin Lei +3
Efficiently managing and utilizing large-scale medical imaging datasets with limited resources presents significant challenges. While coreset selection helps reduce computational c…
Code Fingerprints: Disentangled Attribution of LLM-Generated Code
Jiaxun Guo, Ziyuan Yang, Mengyu Sun +3
The rapid adoption of Large Language Models (LLMs) has transformed modern software development by enabling automated code generation at scale. While these systems improve productiv…
LURE: Latent Space Unblocking for Multi-Concept Reawakening in Diffusion Models
Mengyu Sun, Ziyuan Yang, Andrew Beng Jin Teoh +3
Concept erasure aims to suppress sensitive content in diffusion models, but recent studies show that erased concepts can still be reawakened, revealing vulnerabilities in erasure m…